tile: Provide atomic_{or,xor,and}

Implement atomic logic ops -- atomic_{or,xor,and}.

For tilegx, these are relatively straightforward; the architecture
provides atomic "or" and "and", both 32-bit and 64-bit. To support
xor we provide a loop using "cmpexch".

For the older 32-bit tilepro architecture, we have to extend
the set of low-level assembly routines to include 32-bit "and",
as well as all three 64-bit routines. Somewhat confusingly,
some 32-bit versions are already used by the bitops inlines, with
parameter types appropriate for bitops, so we have to do a bit of
casting to match "int" to "unsigned long".

Signed-off-by: Chris Metcalf <[e-mail]>
Signed-off-by: Peter Zijlstra (Intel) <[e-mail]>
Link: http://lkml.kernel.org/r/[e-mail]
Signed-off-by: Thomas Gleixner <[e-mail]>

arch/tile/include/asm/atomic_32.h

···
 	_atomic_xchg_add(&v->counter, i);
 }
 
+#define ATOMIC_OP(op)							\
+unsigned long _atomic_##op(volatile unsigned long *p, unsigned long mask); \
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	_atomic_##op((unsigned long *)&v->counter, i);			\
+}
+
+#define CONFIG_ARCH_HAS_ATOMIC_OR
+
+ATOMIC_OP(and)
+ATOMIC_OP(or)
+ATOMIC_OP(xor)
+
+#undef ATOMIC_OP
+
 /**
  * atomic_add_return - add integer and return
  * @v: pointer of type atomic_t
···
 {
 	_atomic64_xchg_add(&v->counter, i);
 }
+
+#define ATOMIC64_OP(op)						\
+long long _atomic64_##op(long long *v, long long n);		\
+static inline void atomic64_##op(long long i, atomic64_t *v)	\
+{								\
+	_atomic64_##op(&v->counter, i);				\
+}
+
+ATOMIC64_OP(and)
+ATOMIC64_OP(or)
+ATOMIC64_OP(xor)
 
 /**
  * atomic64_add_return - add integer and return
···
 extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
 						  int *lock, int o, int n);
 extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic_and(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
 extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
 extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
···
 					long long n);
 extern long long __atomic64_xchg_add_unless(volatile long long *p,
 					int *lock, long long o, long long n);
+extern long long __atomic64_and(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_or(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_xor(volatile long long *p, int *lock, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);

arch/tile/include/asm/atomic_64.h

···
 	return oldval;
 }
 
+#define CONFIG_ARCH_HAS_ATOMIC_OR
+
+static inline void atomic_and(int i, atomic_t *v)
+{
+	__insn_fetchand4((void *)&v->counter, i);
+}
+
+static inline void atomic_or(int i, atomic_t *v)
+{
+	__insn_fetchor4((void *)&v->counter, i);
+}
+
+static inline void atomic_xor(int i, atomic_t *v)
+{
+	int guess, oldval = v->counter;
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch4(&v->counter, guess ^ i);
+	} while (guess != oldval);
+}
+
 /* Now the true 64-bit operations. */
 
 #define ATOMIC64_INIT(i)	{ (i) }
···
 		oldval = cmpxchg(&v->counter, guess, guess + a);
 	} while (guess != oldval);
 	return oldval != u;
+}
+
+static inline void atomic64_and(long i, atomic64_t *v)
+{
+	__insn_fetchand((void *)&v->counter, i);
+}
+
+static inline void atomic64_or(long i, atomic64_t *v)
+{
+	__insn_fetchor((void *)&v->counter, i);
+}
+
+static inline void atomic64_xor(long i, atomic64_t *v)
+{
+	long guess, oldval = v->counter;
+	do {
+		guess = oldval;
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch(&v->counter, guess ^ i);
+	} while (guess != oldval);
 }
 
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))

arch/tile/lib/atomic_32.c

···
 }
 EXPORT_SYMBOL(_atomic_or);
 
+unsigned long _atomic_and(volatile unsigned long *p, unsigned long mask)
+{
+	return __atomic_and((int *)p, __atomic_setup(p), mask).val;
+}
+EXPORT_SYMBOL(_atomic_and);
+
 unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask)
 {
 	return __atomic_andn((int *)p, __atomic_setup(p), mask).val;
···
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
+long long _atomic64_and(long long *v, long long n)
+{
+	return __atomic64_and(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_and);
+
+long long _atomic64_or(long long *v, long long n)
+{
+	return __atomic64_or(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_or);
+
+long long _atomic64_xor(long long *v, long long n)
+{
+	return __atomic64_xor(v, __atomic_setup(v), n);
+}
+EXPORT_SYMBOL(_atomic64_xor);
 
 /*
  * If any of the atomic or futex routines hit a bad address (not in

arch/tile/lib/atomic_asm_32.S

···
 atomic_op _xchg_add_unless, 32, \
 	"sne r26, r22, r2; { bbns r26, 3f; add r24, r22, r3 }"
 atomic_op _or, 32, "or r24, r22, r2"
+atomic_op _and, 32, "and r24, r22, r2"
 atomic_op _andn, 32, "nor r2, r2, zero; and r24, r22, r2"
 atomic_op _xor, 32, "xor r24, r22, r2"
 
···
 	{ bbns r26, 3f; add r24, r22, r4 }; \
 	{ bbns r27, 3f; add r25, r23, r5 }; \
 	slt_u r26, r24, r22; add r25, r25, r26"
+atomic_op 64_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
+atomic_op 64_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
+atomic_op 64_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
 
 	jrp     lr              /* happy backtracer */